Compare AI models

Specifications
Parameters
7B—
Context window
4k128k
These models have no shared benchmark scores.
Overview
CompanyDeepSeekMistral
Release dateFeb 5 2024Jul 10 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-Math and Devstral Medium don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek-Math shipped 521 days before Devstral Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 4k (DeepSeek-Math) vs 128k (Devstral Medium). DeepSeek-Math is open weight, while Devstral Medium is closed.

Direct benchmark comparisons are unavailable — DeepSeek-Math and Devstral Medium don't publish scores on any of the same benchmarks.